Choose tools for designing proteins that bind a target. Compare BoltzGen, BindCraft, RFdiffusion, and Germinal by target type, design diversity, and validation needs, then plan target preparation, design generation, and candidate filtering.
中文简介正在准备中。当前显示英语简介。
Guidance for choosing the right protein binder design tool. Use this skill when: (1) Deciding between BoltzGen, BindCraft, or RFdiffusion, (2) Planning a binder design campaign, (3) Understanding trade-offs between different approaches, (4) Selecting tools for specific target types. For specific tool parameters, use the individual tool skills (boltzgen, bindcraft, rfdiffusion, etc.).
安装前可以查看交给 AI 代理的指令内容。
De novo binder design?
│
├─ Standard target → BoltzGen (recommended)
│ All-atom output (no separate ProteinMPNN step needed)
│ Better for ligand/small molecule binding
│ Single-step design (backbone + sequence + side chains)
│
├─ Need diversity/exploration → RFdiffusion + ProteinMPNN
│ Maximum backbone diversity
│ Two-step: backbone then sequence
│
├─ Integrated validation → BindCraft
│ Built-in AF2 validation
│ End-to-end pipeline
│
├─ Ligand binding → BoltzGen ✓
│ All-atom diffusion handles ligand context
│
├─ Peptide/nanobody → Germinal
│ VHH/nanobody design
│ Germline-aware optimization
│
└─ Antibody/Nanobody
+-- VHH design --> germinal skill
| Tool | Strengths | Weaknesses | Best For |
|---|---|---|---|
| BoltzGen | All-atom, single-step, ligand-aware | Higher GPU requirement | Standard (recommended) |
| BindCraft | End-to-end, built-in AF2 validation | Less diverse | Production campaigns |
| RFdiffusion | High diversity, fast | Requires ProteinMPNN | Exploration, diversity |
| Germinal | Nanobody/VHH design | Specialized | Antibody optimization |
BoltzGen provides all-atom design with built-in side-chain packing:
Target → BoltzGen → Validate → Filter
(pdb) (all-atom) (chai) (qc)
# Fetch structure from PDB
# Use pdb skill for guidance
First, create a YAML config file (e.g., binder.yaml):
entities:
- protein:
id: B
sequence: 70..100
- file:
path: target.cif
include:
- chain:
id: A
binding_types:
- chain:
id: A
binding: 45,67,89
Then run:
modal run modal_boltzgen.py \
--input-yaml binder.yaml \
--protocol protein-anything \
--num-designs 50
Why BoltzGen?
For maximum diversity or when backbone-only is preferred:
# Step 1: Backbone generation
modal run modal_rfdiffusion.py \
--pdb target.pdb \
--contigs "A1-150/0 70-100" \
--hotspot "A45,A67,A89" \
--num-designs 500
# Step 2: Sequence design
modal run modal_ligandmpnn.py \
--pdb-path backbone.pdb \
--num-seq-per-target 16 \
--sampling-temp 0.1
modal run modal_chai1.py \
--input-faa sequences.fasta \
--out-dir predictions/
Apply standard thresholds:
See protein-qc skill for details.
| Stage | Count | Purpose |
|---|---|---|
| Backbone generation | 500-1000 | Diversity |
| Sequences per backbone | 8-16 | Sequence space |
| AF2 predictions | All | Validation |
| After filtering | 50-200 | Candidates |
| Experimental testing | 10-50 | Final selection |
| Step | Compute Time |
|---|---|
| RFdiffusion (500 designs) | 2-4 hours |
| ProteinMPNN (8000 sequences) | 1-2 hours |
| AF2 prediction (8000 sequences) | 12-24 hours |
| Filtering and analysis | 1-2 hours |
Total: 1-2 days of compute
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Support protein design with cloud laboratory testing for binding, expression, thermal stability, and enzyme activity. Covers sequence optimization, submitting experiments through the Adaptyv API, checking progress, and downloading experimental results.
中文简介正在准备中。当前显示英语简介。
Build flexible daily plans that account for ADHD-related difficulties with time estimation and getting started. Narrow priorities to three tasks, add transition buffers, and choose small next actions that match the energy available that day.
中文简介正在准备中。当前显示英语简介。
Build Python workflows for data recorded over time, including classification, forecasting, anomaly detection, and pattern search. Using aeon, the skill guides preprocessing, algorithm selection, feature extraction, and evaluation through interfaces compatible with scikit-learn.
中文简介正在准备中。当前显示英语简介。
Use a browser to research topics, extract page information, fill forms, and test websites. Guides agents through identifying page controls, interacting with web apps, saving screenshots or PDFs, and reusing saved login sessions.
中文简介正在准备中。当前显示英语简介。
Combine health measurements, exercise, sleep, nutrition, and mental health records to examine trends, unusual changes, and estimated risks. The skill produces personalized suggestions and text or interactive HTML reports using local data without external API calls.
中文简介正在准备中。当前显示英语简介。
Predict structures for designed protein sequences and protein complexes with AlphaFold2 or ColabFold. Inspect structure files and confidence scores to assess folding and chain interfaces, with guidance for local runs, Modal execution, and common prediction errors.
中文简介正在准备中。当前显示英语简介。